machine_learn/linear/train_5d.py

#!/usr/bin/python
# -*- coding: UTF-8 -*-
'''
最简单的mse
'''
import sys
import os
sys.path.append(os.path.abspath('..'))
from util.config import config
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from sklearn.model_selection import train_test_split
from draw import draw_util
import joblib


def curce_data(x,y,y_pred):
    x=x.tolist()
    y=y.tolist()
    y_pred=y_pred.tolist()
    results=zip(x,y,y_pred)
    results=["{},{},{}".format(s[0],s[1][0],s[2][0]) for s in results ]
    return results


def read_data(path):
    with open(path) as f :
        lines=f.readlines()
    lines=[eval(line.strip()) for line in lines]
    X,z,y=zip(*lines)
    X=np.array(X)
    y=np.array(y)
    return X,y


def demo(file, model_file):
    X_train,y_train=read_data(file)
    # X_test,y_test=read_data(config.get('application', 'test_data_path'))
    Xtrain, Xtest, Ytrain, Ytest = train_test_split(X_train, y_train, test_size=0.3)
    # 一个对象，它代表的线性回归模型，它的成员变量，就已经有了w，b. 刚生成w和b的时候 是随机的
    model = LinearRegression()
    # 一调用这个函数，就会不停地找合适的w和b 直到误差最小
    model.fit(Xtrain, Ytrain)
    # 打印W
    # print(model.coef_)
    # 打印b
    print(model.intercept_)
    # 模型已经训练完毕,用模型看下在训练集的表现
    y_pred_train = model.predict(Xtrain)
    # sklearn 求解训练集的mse
    # y_train 在训练集上 真实的y值
    # y_pred_train 通过模型预测出来的y值
    # 计算  (y_train-y_pred_train)^2/n
    train_mse = metrics.mean_squared_error(Ytrain, y_pred_train)
    print("训练集MSE:", train_mse)

    # 看下在测试集上的效果
    y_pred_test = model.predict(Xtest)
    # print(y_pred_test)
    test_mse = metrics.mean_squared_error(Ytest, y_pred_test)
    print("测试集MSE:",test_mse)
    # 保存模型
    joblib.dump(model,  model_file)

def draw_line():
    x_train, y_train = read_data("../bbztx/train_data")
    print(x_train.tolist())
    print(y_train.tolist())
    draw_util.drawScatter(x_train.tolist(), y_train.tolist())


if __name__ == '__main__':
    root_dir = 'D:\\data\\quantization\\5d\\'
    model_dir = 'D:\\data\\quantization\\5d_lr_model\\'
    list = os.listdir(root_dir)
    for f in list:
        print(f)
        m = f.split('.')[0][-6:]
        demo(root_dir + str(f), model_dir + '' + str(m) + '.pkl')